paper-with-me

Papers

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL

2024-12-13 · Yang Qin, Chao Chen, Zhihang Fu, Ze Chen, Dezhong Peng, Peng Hu, Jieping Ye

Despite the significant advancements in Text-to-SQL (Text2SQL) facilitated by large language models (LLMs), the latest state-of-the-art techniques are still trapped in the in-context learning of closed-source LLMs (e.g., GPT-4), which limits their applicability in open scenarios. To address this challenge, we propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2SQL, thereby providing a more practical solution. Our approach begins with multi-task supervised fine-tuning (SFT) using various synthetic training data related to SQL generation. Unlike existing SFT-based Text2SQL methods, we introduced several additional SFT tasks, including schema linking, noise correction, and continuation writing. Engaging in a variety of SQL generation tasks enhances the model's understanding of SQL syntax and improves its ability to generate high-quality SQL queries. Additionally, inspired by the collaborative modes of LLM agents, we introduce a Multitask Collaboration Prompting (MCP) strategy. This strategy leverages collaboration across several SQL-related tasks to reduce hallucinations during SQL generation, thereby maximizing the potential of enhancing Text2SQL performance through explicit multitask capabilities. Extensive experiments and in-depth analyses have been performed on eight open-source LLMs and five widely-used benchmarks. The results demonstrate that our proposal outperforms the latest Text2SQL methods and yields leading performance.

📄 PDF Abstract BibTeX arXiv:2412.10138

Code (1)

alibaba/route 공식 구현 pytorch

Tasks

In-Context LearningText to SQLText-To-SQL

Methods 이 논문이 사용한 방법론

SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

GraphLoRA: Empowering LLMs Fine-Tuning via Graph Collaboration of MoE

2024-12-18 · Ting Bai, Yue Yu, Le Huang, Zenan Xu 외

Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning method that has been widely adopted in various downstream applications of LLMs. Together with the Mixture-of-Expert (MoE) technique, fine-tuning approaches …

parameter-efficient fine-tuning

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing

2022-11-02 · Yonggan Fu, Yang Zhang, Kaizhi Qian, Zhifan Ye 외

Self-supervised learning (SSL) for rich speech representations has achieved empirical success in low-resource Automatic Speech Recognition (ASR) and other speech processing tasks, which can mitigate the necessity of a la…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learningspeech-recognition+1

Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning

2024-04-13 · Yijiang Liu, Rongyu Zhang, Huanrui Yang, Kurt Keutzer 외

Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications, ranging from content generation to interactive entertainment, and artistic creation. However, …

DiversityMixture-of-Experts

Token-Level LLM Collaboration via FusionRoute

2026-01-08 · Nuoya Xiong, Yuhang Zhou, Hanqing Zeng, Zhaorun Chen 외 arxiv

Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a single general-purpose model typically requires scaling to sizes that are prohibiti…

Mathematical ReasoningInstruction FollowingCode Generation

Enhancing Multimodal Continual Instruction Tuning with BranchLoRA

2025-05-31 · Duzhen Zhang, Yong Ren, Zhong-Zhi Li, Yahan Yu 외

Multimodal Continual Instruction Tuning (MCIT) aims to finetune Multimodal Large Language Models (MLLMs) to continually align with human intent across sequential tasks. Existing approaches often rely on the Mixture-of-Ex…

Mixture-of-Experts